For large-scale hyperspectral image data, how to retrieve the satisfied information quickly and accurately is critical. As hyperspectral images are one of the important fundamental and strategic information resources, it is necessary to ensure data security during the retrieval process. A secure retrieval method of hyperspectral images in an encrypted domain is proposed. The main contributions are fourfold: (1) for accurately describing the hyperspectral image content, spectral words are created to represent the spectral feature of hyperspectral image and the gray level cooccurrence matrix is computed as the texture feature; (2) the hyperspectral images are protected using a hybrid domain encryption method; (3) an order preserving encryption method is utilized to encrypt the spectral words and texture feature for secure retrieval; and (4) the retrieval results are obtained by matching Jaccard distance in the encrypted domain and then further optimized by the user’s relevance feedback. The experimental results show that our secure retrieval method can effectively improve the retrieval accuracy of a hyperspectral image as well as guarantee the security of the image content.