In this paper, an image retrieval algorithm is proposed based on lifting wavelet, for it has many advantages such as high efficiency and resolution. Firstly, through lifting wavelet transform of the image, we can get each layer of the low-frequency sub-image and high-frequency sub-images. Then, shape feature of low-frequency sub-image and texture feature of high-frequency sub-images can be extracted. Finally, the Euclidean distance is calculated between the feature vectors and retrieved similar images. Experimental results show that the retrieval efficiency of this algorithm is better than other algorithms. It has advantages and versatility.