It is now well established that galaxy interactions and mergers play a crucial role in the hierarchical growth of structure in our universe. Galaxy mergers can lead to the formation of elliptical galaxies and larger disk galaxies, as well as drive galaxy evolution through star formation and nuclear activity. During mergers, the nuclei of the individual galaxies come closer and finally form a double nuclei galaxy. Although mergers are common, the detection of double-nuclei galaxies (DNGs) is rare and fairly serendipitous. Their detection is very important as their properties can help us understand the formation of supermassive black hole (SMBH) binaries, dual active galactic nuclei (DAGN), and the associated feedback effects. There is thus a need for an automatic/systematic survey of data for the discovery of double nuclei galaxies. Using the Sloan digital sky survey (SDSS) as the target catalog, we have introduced a novel algorithm "Gothic" (Graph-bOosTed iterated HIll Climbing) that detects whether a given image of a galaxy has characteristic features of a DNG (ASCL entry 2707). We have tested the algorithm on a random sample of 100,000 galaxies from the Stripe 82 region in SDSS and obtained a maximum detection rate of 4.2% with a careful choice of the input catalog.