Search engines have already crawled the visual web. Crawling it all again would duplicate that work, along with the hardware, energy and water behind it. I use their indexes as the first stage of a copy-detection pipeline and do all of the verification myself, on one Mac mini.
Source: [Dev.to](https://dev.to/levent_celiksan_617dcb736/how-i-find-edited-copies-of-images-across-the-web-without-crawling-it-30ep)