Generating reports for computed tomography (CT) images is a challenging task. Although it is related to existing work on medical image report generation, it exhibits several unique characteristics, including the spatial encoding of multiple images and the alignment between image volumes and text. Existing solutions typically use general 2D or 3D image processing techniques to extract features from a CT volume, where they firstly compress the volume and then divide the compressed CT slices into patches for visual encoding. These approaches do not explicitly account for the transformations among CT slices, nor do they effectively integrate multi-level image features, particularly those containing specific organ lesions, to instruct CT report generation (CTRG). In considering the strong correlation among consecutive slices in CT scans, in this paper, we propose a large language model (LLM) based CTRG method with recurrent visual feature extraction and stereo attentions for hierarchical feature modeling. Specifically, we use a vision Transformer to recurrently process each slice in a CT volume, and employ a set of attentions over the encoded slices from different perspectives to selectively obtain important visual information and align it with textual features, so as to better instruct an LLM for CTRG. Experiment results and further analysis on the benchmark M3DCap dataset show that our method outperforms strong baseline models and achieves state-of-the-art results, demonstrating its validity and effectiveness11Code is available at https://github.com/synlp/SA-CTRG