The Internet plays a key role in accomplishing many tasks. For many such tasks, web search is integral in finding relevant information. Similar to other domains, web search is also heavily used in software engineering (SE) to help with various SE specific tasks such as debugging, finding documentation, installation, etc. In this paper, we present the first large scale study on how web search is used in software engineering and maintenance. We analyze the query logs from a major commercial web search engine. Being able to disambiguate software engineering queries from other queries is important for understanding the usage of web search in software engineering. To this end, we build a machine learning based classifier to identify software engineering queries. We then analyze 1 million web search sessions to understand how software engineering related queries and sessions differ from other queries and sessions. Subsequently, we define the taxonomy of intents behind the usage of web search by software engineers. This allows us to develop a better understanding of the various contexts in which web search is used in software engineering and maintenance. We then analyse 6 million SE queries to understand the distribution of intents across various web search metrics and other trend characteristics. Our results show that web search is heavily used for various software engineering and maintenance tasks. Finally, we discuss the implications of this work on improving search engine support for software engineering queries by providing contextual assistance and we elaborate on how we can gain insights into common issues faced by developers which can be leveraged to improve and maintain different software technologies.