The content-based image retrieval on histogram was analyzed and a novel image retrieval algorithm was proposed based on bit-plane distribution feature. Firstly, the feature of the noise was considered and the image is divided into eight bit-planes by the image bit-plane-code. Then, the Bit-plane Distribution Feature (BPDF) was constructed　according to statistic distribution of the four significant planes which contain most of the structural information of the image. Meantime, the gray-code of bit-planes was used to avoid the effect of changes in the image intensity values on bit-planes. Finally the Mahalanobis distance was adopted to measure the similarity because of the correlation between the concerned vectors after designing the correlation-weighted matrix. Experimental results show that the proposed method has sound retrieval performance.