Content-Based Image Retrieval applications have been rapidly developed along with the increase in the quantity availability and importance of images in our daily life. However, the wide deployment of Content-Based Image Retrieval scheme has been limited by its the server computation and storage requirement. Privacy-Preserving Content-Based Image Retrieval scheme, which allows the data owner to outsource the image database and Content-Based Image Retrieval service to the cloud, without revealing the actual content of the database to the cloud server. Local features are utilized to represent the images, and Earth Mover's Distance is employed to evaluate the similarity of images. The proposed scheme transforms the Earth Mover's Distance problem in such a way that the cloud server can solve it without learning sensitive information. The security analysis and experiments show the security an efficiency of the proposed scheme using a Secure Hash Algorithm.