We present a rank-based voting technique utilizing inclusion relationship for high-quality image search. Since images can have multiple regions of interest, we extract representative object regions using a state-of-the-art region proposal method tailored for our search problem. We then extract CNN features locally from those representative regions and identify inclusion relationship between those regions. To identify similar images given a query, we propose a novel similarity measure based on representative regions and their inclusion relationship. Our similarity measure gives a high score to a pair of images that contain similar object regions with similar spatial arrangement. To verify benefits of our method, we test our method in three standard benchmarks and compare it against the state-of-the-art image search methods using CNN features. Our experiment results demonstrate effectiveness and robustness of the proposed algorithm.