Our skin lesion classification algorithm won the international ISIC 2018 Skin Lesion Diagnosis Challenge by a large margin. Participants were provided with a held-out test set to predict the diagnosis of 1512 skin lesions from 7 possible disease classes. Our method scored a balanced accuracy of 88.5% across all 7 classes and is undergoing clinical trials for further evaluation of its use alongside practicing physicians. If proved clinically successful, this holds the potential to be used as an invaluable decision support tool capable of screening a large number of skin lesions, allowing for the most concerning cases to receive priority attention. Until then, the Visual Search tool is to be used in an educational capacity to show similar cases and help as a learning tool for identification and matching.